Neel Nanda(@NeelNanda5):I thought this was an excellent paper! Thanks to Anthropic for asking me to write a review of it, linked below I've long suspected that models have some kind of "working memory" to store intermediate variables during a forward pass and IMO this paper has the best evidence yet

Neel Nanda

@NeelNanda5

Mechanistic Interpretability lead DeepMind. Formerly @AnthropicAI, independent. In this to reduce AI X-risk. Neural networks can be understood, let's go do it!

加入 June 2022

122 正在關注 47.5K 粉絲

Neel Nanda@NeelNanda5

2026.07.06 18:09

I thought this was an excellent paper! Thanks to Anthropic for asking me to write a review of it, linked below I've long suspected that models have some kind of "working memory" to store intermediate variables during a forward pass and IMO this paper has the best evidence yet